Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context by stating the result is 'bounded' (respecting limit/offset) and 'reproducible' (deterministic ordering/selection), which is not captured in annotations. No contradiction with openWorldHint=false or destructiveHint=false exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single 11-word sentence with no filler or redundancy. It is front-loaded with the action verb and defines the core constraint in the first clause. Every word contributes to the meaning, achieving high information density without sacrificing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description is inadequate for a tool with 8 parameters and zero schema coverage. It leaves unknown what metrics are required, how the filter parameters interact, what a 'GERDA dataset' is, and how pagination or ordering works beyond the vague 'bounded, reproducible.' An agent would still need substantial external knowledge or experimentation to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the 8 parameters, but it does not. It mentions 'subset' and 'bounded' which allude to filtering and limit/offset behavior, but it never explains what 'dataset', 'metrics', 'ags', 'years', 'states', or 'counties' mean within this domain. The description adds almost no value beyond the raw parameter names listed in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Return') and a clear resource ('bounded, reproducible subset of a published GERDA dataset'), making the core purpose obvious. It does not explicitly contrast with siblings like get_download or describe_dataset, but the focus on 'subset' versus full datasets is mildly distinguishing. The phrasing is clear enough that an agent won't confuse it with list_datasets or find_geographies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus siblings; alternatives are not named. It does not mention conditions for choosing query_results over get_download, describe_dataset, or list_datasets. The agent is left to infer that this tool returns data rows, but there is no explicit 'use when' or 'prefer X instead' statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.